© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3019
    Prev
    Next
    INDEX
    Explanations

    say 乾隆

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dev
    -21.00
     Dev
    -21.00
    Dev
    -20.25
    dev
    -19.38
    (seg
    -18.25
    tab
    -18.13
    tsx
    -17.25
    _dev
    -17.13
    (dev
    -17.13
    .Dev
    -16.88
    POSITIVE LOGITS
    乾隆
    34.25
    OT
    18.75
     Merlin
    17.88
    ERIC
    16.63
    ERM
    16.38
    erg
    16.25
    Bern
    15.44
     OT
    15.25
    rew
    14.88
    OTO
    14.81
    Activations Density 0.019%

    No Known Activations